STORM: A Spatio-Temporal Context-Aware Model for Predicting Event-Triggered Abnormal Crowd Traffic
- 29 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (10) , 13051-13066
Abstract
Urban events, such as hurricanes, floods, and epidemic outbreaks, usually have a significant impact on crowd behaviors that may dramatically change people’s mobility patterns, interaction manners, and etc. Accurately foreseeing the abnormal crowd behaviors triggered by urban events can help authorities to dynamically schedule urban resources and services, such as providing shuttle buses, temporal shelters, and psychological first aid. However, traditional crowd behavior prediction models tend to learn regular trends and patterns of crowd traffic, and usually fail to predict the abnormal traffic fluctuations triggered by urban events. In this work, we propose a context-aware framework to accurately predict event-triggered abnormal crowd traffic by explicitly modeling event contexts and their impact. We start by training a state-of-the-art spatiotemporal multi-graph model (MG) leveraging a multi-graph convolutional network (MGCN) to model city-wide venues and their connections, as well as gated recurrent unit (GRU) to capture the crowd traffic patterns within venues. In order to model the time-occasional impact of sudden influential event context (e.g., weather conditions), we propose a multi-task fusion diagram to co-train the MG model by learning a temporal impact embedding with an attention mechanism and recurrent neural network to obtain the MG-MT model. In order to model the hyper-space impact of irregularly distributed event context (e.g., epicenters and trajectories), we propose a multi-view fusion diagram to fine-tune the above-mentioned model by learning a spatial impact graph with a stimulus-response mechanism to obtain the spatiotemporal crowd traffic model (STORM). Experiments using real-world urban data collected from Xiamen, China show that our approach improves over the state-of-the-art baseline by more than 6% in predicting crowd traffic and by more than 40% in the abnormal crowd traffic part.Keywords
Funding Information
- National Natural Science Foundation of China (61802325)
This publication has 40 references indexed in Scilit:
- Forecasting the subway passenger flow under event occurrences with multivariate disturbancesExpert Systems with Applications, 2022
- Analyzing spatio-temporal impacts of extreme rainfall events on metro ridership characteristicsPhysica A: Statistical Mechanics and its Applications, 2021
- Analysis of natural and man-made accidents happened in subway stations and trains: based on statistics of accident casesMATEC Web of Conferences, 2019
- Short-term forecasting of passenger demand under on-demand ride services: A spatio-temporal deep learning approachTransportation Research Part C: Emerging Technologies, 2017
- A comparative study to determine the optimal copula model for the wind speed and precipitation of typhoonsInternational Journal of Climatology, 2016
- Forecasting holiday daily tourist flow based on seasonal support vector regression with adaptive genetic algorithmApplied Soft Computing, 2015
- Regression conformal prediction with random forestsMachine Learning, 2014
- Vector Autoregressive Models for Multivariate Time Series2007
- Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical ResultsJournal of Transportation Engineering, 2003
- Distributed representations, simple recurrent networks, and grammatical structureMachine Learning, 1991